Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hxy91819/mason-skills --skill distillgit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hxy91819/mason-skills/distill)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/distill"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/distill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/distill"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/distill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.02425 |
| Opus 5.5 | $0.00028 | $0.00970 |
| Sonnet 5.5 | $0.00014 | $0.00485 |
| Haiku 4.5 | $0.00007 | $0.00243 |
Grade A, and why
distill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill Session Evidence into the Harness and Project Knowledge
Turn session evidence into the smallest verified changes that make future work more
reliable. The harness is everything that shapes an agent's run: intent and specs, the
applicable AGENTS.md chain, repository Skills and their invocation metadata, tools and
scripts, environment and permissions, and verification. Project knowledge is the
durable documentation and decision rationale that give humans and agents an accurate
global view of the project.
Run the four phases in order. Phase 3 is the single approval gate: the user's confirmation of the candidate set authorizes its smallest in-scope edits. Ask again only for a materially different target, an external repository, or a destructive change. Finish without edits when no candidate survives.
The evidence is the current conversation and its tool output. Other sessions are out of scope; a pattern that spans sessions shows up here when an existing rule or Skill failed to prevent it again.
Phase 1: Replay
Reconstruct the trajectory and record:
- The intended outcome and acceptance criteria.
- Actions, tool feedback, failures, retries, and repeated work.
- Every explicit user correction, clarification, or rejected assumption, as a belief delta: what the agent believed, what the user established, and the intended scope.
- Every non-obvious gotcha whose root cause and recovery were verified, kept apart from the ordinary error that exposed it.
- Shortcuts worth making repeatable, and interaction friction (avoidable questions, excessive output).
- Every repository instruction or Skill that shaped the work: missed or surprising invocation, unclear steps, ignored guidance, and places the user had to compensate.
- Every durable decision the user made or clarified, with its rationale and constraints.
- Every material decision the agent introduced, what consequences were disclosed, and whether the user confirmed it.
Compare the actual path with the shortest reliable one. Classify each signal as a harness gap, project-knowledge gap, execution defect, environment or tool defect, request ambiguity, or one-off. An agent mistake becomes a harness candidate only when the harness could reliably prevent, expose, or shorten it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +2 lines 375fa6fd8850
- 1mo ago Changed · -225 lines · -17 tokens per session 5e9fe3860ca9
- 1mo ago Changed · +1 lines 44ded5a5d802
- 1mo ago Changed · +2 lines aa8a0db4d929
- 1mo ago Changed · +24 lines fa2d30dd9ab5
- 2mo ago First seen · 403 lines · 86 tokens per session scan A 32cf02578181
distill is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 2,425 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
distill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| distillhxy91819/mason-skills | Skill | 3 | today | MIT | A | 69 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | today | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | yesterday | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 0 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |